fmi-basel/latent-predictive-learning

Code to accompany our paper "The combination of Hebbian and predictive plasticity learns invariant object representations in deep sensory networks"

39
/ 100
Emerging

This project provides code to help neuroscientists and computational biologists explore how the brain learns to recognize objects without explicit labels. By feeding in images or sensory data, it trains a neural network using a novel biologically-inspired learning rule and outputs insights into the network's learned representations, mimicking how biological sensory systems might process information. This is for researchers modeling brain function or developing self-supervised learning algorithms.

No commits in the last 6 months.

Use this if you are a neuroscience or AI researcher interested in understanding or simulating how biological neural networks learn invariant object representations through self-supervised and Hebbian-like plasticity.

Not ideal if you're looking for a pre-trained model or a high-level API to immediately apply to a computer vision task without deep engagement in the underlying learning mechanisms.

computational-neuroscience biologically-inspired-AI self-supervised-learning neural-network-modeling sensory-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

31

Forks

7

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fmi-basel/latent-predictive-learning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.